https://github.com/esengine/deepseek-reasonix
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
https://github.com/esengine/deepseek-reasonix
agent agent-framework ai-agent ai-coding cli coding-agent deepseek developer-tools ink llm prompt-caching r1 terminal tool-use tui typescript
Last synced: 19 days ago
JSON representation
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
- Host: GitHub
- URL: https://github.com/esengine/deepseek-reasonix
- Owner: esengine
- License: mit
- Created: 2026-04-21T08:27:02.000Z (about 1 month ago)
- Default Branch: main
- Last Pushed: 2026-05-06T08:59:03.000Z (27 days ago)
- Last Synced: 2026-05-06T09:14:45.021Z (27 days ago)
- Topics: agent, agent-framework, ai-agent, ai-coding, cli, coding-agent, deepseek, developer-tools, ink, llm, prompt-caching, r1, terminal, tool-use, tui, typescript
- Language: TypeScript
- Homepage: https://esengine.github.io/deepseek-reasonix/
- Size: 6.07 MB
- Stars: 387
- Watchers: 1
- Forks: 24
- Open Issues: 18
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.md
- Funding: .github/FUNDING.yml
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Security: SECURITY.md
Awesome Lists containing this project
README
English
·
简体中文
·
Website
·
Guide
·
Architecture
·
Benchmarks
A DeepSeek-native AI coding agent for your terminal.
Engineered around prefix-cache stability — so token costs stay low across long sessions, and you can leave it running.
> [!TIP]
> **Cache stability isn't a feature you turn on; it's an invariant the loop is designed around.** That's the whole reason Reasonix is DeepSeek-only — every layer is tuned to the byte-stable prefix-cache mechanic.
> [!NOTE]
> **Real user, single day (2026-05-01):** 435M input tokens, **99.82% cache hit**, ~$12 instead of the ~$61 the same workload would cost with no cache on `v4-flash` — see the [case study](./benchmarks/real-world-cache/README.md). DeepSeek provides the cacheable bytes; the four mechanisms in [Pillar 1](./docs/ARCHITECTURE.md#pillar-1--cache-first-loop) are how Reasonix keeps them cacheable across long sessions.
## Install
Requires Node ≥ 22. Works on macOS · Linux · Windows (PowerShell · Git Bash · Windows Terminal).
Install Reasonix globally if you want the `reasonix` command available on your `PATH`:
```bash
npm install -g reasonix
reasonix code my-project # paste a DeepSeek API key on first run; persists after
```
Or run it once without installing globally:
```bash
cd my-project
npx reasonix code # always uses the latest package by default
```
Grab a [DeepSeek API key →](https://platform.deepseek.com/api_keys) · `reasonix code --help` for flags.
If you use Reasonix daily, global install is the simplest path. If you just want to try it, use `npx`.
| Command | When |
|---|---|
| `reasonix code [dir]` | The coding agent. **Start here.** |
| `reasonix chat` | Plain chat — no filesystem or shell tools. |
| `reasonix run "task"` | One-shot, streams to stdout. Good for pipes. |
| `reasonix doctor` | Health check: Node, API key, MCP wiring. |
| `reasonix update` | Upgrade Reasonix itself. |
Other subcommands (`replay` · `diff` · `events` · `stats` · `index` · `mcp` · `prune-sessions`) are in `reasonix --help` and the [CLI reference](https://esengine.github.io/DeepSeek-Reasonix/#cli).
### Desktop client (prerelease)
A native Tauri client for users who want a GUI over the same loop. Multi-tab, the right-panel shows files the agent has read or edited this session, the same cost / cache / token meters live at the bottom. Same DeepSeek API key, same `~/.reasonix` config — the desktop bundles its own Node runtime, no separate `npm install` step.
Download platform installers from [GitHub Releases](https://github.com/esengine/DeepSeek-Reasonix/releases). The desktop ships as a **prerelease**: the loop and protocol are the same as the CLI, but the UI is still being polished and the installers aren't code-signed yet.
- **macOS** — first launch hits Gatekeeper. One-time fix: `xattr -dr com.apple.quarantine /Applications/Reasonix.app` (or right-click → Open → confirm).
- **Windows** — SmartScreen warns "Unknown publisher". Click **More info → Run anyway**.
- **Linux** — `.deb` and `.AppImage` ship plain, no extra step.
The CLI remains the canonical surface. Anything that lands in the CLI is also available from the desktop's composer.
Working in another folder · chat vs. code · author a skill
**Working in a different folder.** Reasonix scopes filesystem tools to the launch directory; pass `--dir` to retarget. Mid-session switching isn't supported by design (memory paths would tangle with stale roots) — quit and relaunch.
```bash
npx reasonix code --dir /path/to/project
```
**Picking `chat` vs `code`.** `code` is the default and the only mode with filesystem / shell tools and SEARCH/REPLACE review. `chat` is the lighter, tools-off shell — reach for it when you want a thinking partner with MCP attached but no disk access.
| What you get | `code` | `chat` |
|---|---|---|
| Filesystem tools + `edit_file` | ✓ | — |
| SEARCH/REPLACE → `/apply` review | ✓ | — |
| Shell tool (gated) | ✓ | — |
| Plan mode · `/todo` · `/skill new` · `/mcp add` | ✓ | — |
| Memory (`remember` / `recall_memory`) | project + global | global only |
| MCP servers from config · web search · `ask_choice` | ✓ | ✓ |
| Coding system prompt | ✓ | generic |
| Session scope | per-directory | shared default |
**Author your first skill.** No remote registry — write them directly. Edit the file (`description:` frontmatter + body), then `/skill list`. Add `runAs: subagent` to spawn an isolated subagent loop instead of inlining the body.
```bash
/skill new my-skill # /.reasonix/skills/my-skill.md
/skill new my-skill --global # ~/.reasonix/skills for cross-project use
```
## Configuration
One JSON file at `~/.reasonix/config.json` plus per-project overrides under `/.reasonix/`. The full bilingual reference — every key, every slash command, the on-disk shape of skills/memory/hooks — lives at:
> 📘 **[Configuration Guide](https://esengine.github.io/DeepSeek-Reasonix/configuration.html)** · [中文](https://esengine.github.io/DeepSeek-Reasonix/configuration.html?lang=zh)
| Topic | Quick read |
|---|---|
| [MCP servers](https://esengine.github.io/DeepSeek-Reasonix/configuration.html#mcp) | stdio · SSE · Streamable HTTP. One spec format works for both `config.json` and `--mcp`. |
| [Skills](https://esengine.github.io/DeepSeek-Reasonix/configuration.html#skills) | Markdown playbooks the model can invoke. `inline` or `subagent` mode. |
| [Memory](https://esengine.github.io/DeepSeek-Reasonix/configuration.html#memory) | User-private knowledge pinned into the prefix. `user` / `feedback` / `project` / `reference` types. |
| [Hooks](https://esengine.github.io/DeepSeek-Reasonix/configuration.html#hooks) | Shell commands on lifecycle events. `PreToolUse` (gating) · `PostToolUse` · `UserPromptSubmit` · `Stop`. |
| [Permissions](https://esengine.github.io/DeepSeek-Reasonix/configuration.html#permissions) | Per-workspace shell allowlist. Exact-prefix match. |
| [Web search](https://esengine.github.io/DeepSeek-Reasonix/configuration.html#search) | Mojeek by default; switch to self-hosted SearXNG with `/search-engine`. |
| [Semantic index](https://esengine.github.io/DeepSeek-Reasonix/configuration.html#index) | `reasonix index` — local Ollama or any OpenAI-compatible embedding endpoint. |
## What makes Reasonix different
The loop is organized around three pillars. Each one solves a problem generic agent frameworks don't even see — because they were designed for a different cache mechanic.
Click through to the full architecture writeup → [Pillar 1 — Cache-first loop](./docs/ARCHITECTURE.md#pillar-1--cache-first-loop) · [Pillar 2 — Tool-call repair](./docs/ARCHITECTURE.md#pillar-2--tool-call-repair) · [Pillar 3 — Cost control](./docs/ARCHITECTURE.md#pillar-3--cost-control-v06)
## Capabilities
## How it compares
| | Reasonix | Claude Code | Cursor | Aider |
|-----------------------------------|------------------|-------------------|---------------------|--------------------|
| Backend | DeepSeek | Anthropic | OpenAI / Anthropic | any (OpenRouter) |
| License | **MIT** | closed | closed | Apache 2 |
| Cost profile | **low per task** | premium | subscription + use | varies |
| DeepSeek prefix-cache | **engineered** | not applicable | not applicable | incidental |
| Embedded web dashboard | yes | — | n/a (IDE) | — |
| Configurable web search engine | `/search-engine` | — | — | — |
| Persistent per-workspace sessions | yes | partial | n/a | — |
| Plan mode · MCP · hooks · skills | yes | yes | yes | partial |
| Web search (Mojeek + SearXNG) | yes | yes | yes | yes |
| Open community development | yes | — | — | yes |
For live cache-hit rates, costs, and methodology, see [`benchmarks/`](./benchmarks/) — the numbers move with model pricing, so they live with the harness, not in the README.
## Documentation
- [**Architecture**](./docs/ARCHITECTURE.md) — three pillars: cache-first loop, tool-call repair, cost control
- [**CLI Reference**](./docs/CLI-REFERENCE.md) — every shell subcommand, every slash command, every keybinding
- [**Benchmarks**](./benchmarks/) — τ-bench-lite harness, transcripts, cost methodology
- [**Website**](https://esengine.github.io/DeepSeek-Reasonix/) — getting started, dashboard mockup, TUI mockup
- [**Contributing**](./CONTRIBUTING.md) — comment policy, error-handling rules, library-over-hand-rolled
- [**Code of Conduct**](./CODE_OF_CONDUCT.md) · [**Security policy**](./SECURITY.md)
## Community
> [!NOTE]
> Reasonix is open source and community-developed. The contributors wall below isn't decoration — every avatar is a real PR that shipped.
Scoped starter tickets — each with background, code pointers, acceptance criteria, and hints — live under the [`good first issue`](https://github.com/esengine/reasonix/labels/good%20first%20issue) label. Pick anything open.
**Open Discussions — opinions wanted:**
- [#20 · CLI / TUI design](https://github.com/esengine/reasonix/discussions/20) — what's broken, what's missing, what would you change?
- [#21 · Dashboard design](https://github.com/esengine/reasonix/discussions/21) — react against the [proposed mockup](https://esengine.github.io/DeepSeek-Reasonix/design/agent-dashboard.html)
- [#22 · Future feature wishlist](https://github.com/esengine/reasonix/discussions/22) — what would you build into Reasonix next?
**Already using Reasonix and willing to help others discover it?** Publish blog posts, articles, screenshots, talks, or videos to [**Show and tell**](https://github.com/esengine/reasonix/discussions/categories/show-and-tell). The project has no marketing budget — community word of mouth is how new users find it. Sustained advocates earn the badge below, displayed next to the contributors wall once awarded:
**Before your first PR**: read [`CONTRIBUTING.md`](./CONTRIBUTING.md) — short, strict rules (comments, errors, libraries-over-hand-rolled). `tests/comment-policy.test.ts` enforces the comment ones; `npm run verify` is the pre-push gate. By participating you agree to the [Code of Conduct](./CODE_OF_CONDUCT.md). Security issues → [SECURITY.md](./SECURITY.md).
## Non-goals
> [!IMPORTANT]
> Reasonix is opinionated. Some things it deliberately *doesn't* do — listed here so you can pick the right tool for your work.
- **Multi-provider flexibility.** DeepSeek-only on purpose. Coupling to one backend is the feature, not a limitation.
- **IDE integration.** Terminal-first. The diff lives in `git diff`, the file tree in `ls`. The dashboard is a companion, not a Cursor replacement.
- **Hardest-leaderboard reasoning.** Claude Opus still wins some benchmarks. DeepSeek is competitive on coding; if your work is "solve this PhD proof" rather than "fix this auth bug," start with Claude.
- **Air-gapped / fully-free.** Reasonix needs a paid DeepSeek API key. For air-gapped or zero-cost runs see Aider + Ollama or [Continue](https://continue.dev).
## Star History
---
MIT — see LICENSE
Built by the community at esengine/reasonix
Special thanks to AIGC Link for the promotions on XiaoHongShu.